SVM-Based Approach for Predicting Future Ethereum Prices Using Historical Data
Abstract views: 37 , PDF downloads: 25Abstract
Cryptocurrency markets are volatile and complex, presenting challenges for traditional analysis. This study utilizes a Support Vector Machine (SVM) approach to predict Ethereum’s hourly price movements using historical data, including open, high, low, close prices, and trading volume. Analyzing 34,497 hourly records, the SVM model identifies three market regimes: stable conditions, directional trends, and high-volatility events.Stable conditions dominate 72.7% of the data, marked by consistent price movements and moderate trading volumes, indicating consolidation phases. Directional trends, comprising 15.7%, reflect gradual bullish or bearish price shifts influenced by market sentiment or external factors. High-volatility events, representing 11.5%, are characterized by sharp price spikes or crashes, accompanied by increased trading activity.The Silhouette Score of 0.45 highlights the difficulty of segmenting financial data due to overlapping market states. Despite this, the SVM model effectively captures nonlinear patterns, providing valuable insights into Ethereum's price behavior. This research demonstrates the potential of machine learning in cryptocurrency analysis, enabling better market understanding, improved trading strategies, and enhanced risk management. Future work could integrate advanced features and methods to further boost prediction accuracy and model performance.
Downloads
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[2] Kamruzzaman, J., & Sarker, R. A. (2004). Neural Networks and Support Vector Machines in Predicting Stock Market Trends. Proceedings of the International Conference on Neural Information Processing, 1, 91–96.
[3] Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting Stock and Stock Price Index Movement Using Trend Deterministic Data Preparation and Machine Learning Techniques. Expert Systems with Applications, 42(1), 259–268.
[4] Nakamoto, S. (2008). Bitcoin: A Peer-to-Peer Electronic Cash System. Retrieved from https://bitcoin.org/bitcoin.pdf
[5] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
[6] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
[7] Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer-Verlag.
[8] Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
[9] Zheng, Z., Xie, S., Dai, H.-N., Chen, X., & Wang, H. (2018). Blockchain Challenges and Opportunities: A Survey. International Journal of Web and Grid Services, 14(4), 352–375.
[10] Larsen, D., & Coleman, S. (2016). Analyzing Cryptocurrency Markets Using Machine Learning. Journal of Financial Data Science, 3(2), 10–21.
[11] Fama, E. F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383–417.
[12] Jang, H., & Lee, J. (2017). An Empirical Reaserch on Modeling and Prediction of Bitcoin Prices with Bayesian Neural Networks Based on Blockchain Information. IEEE Access, 6, 5427–5437.
[13] van Steenis, H. (2018). Machine Learning in Financial Markets. Financial Stability Review, 22, 112–120.
[14] Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
